- Type
- MCP
- Transport
- stdio
- Open source
- Yes
- GitHub Stars
- ★ 4.6k
- Source
- mcp-github
- Repository
- github.com/Gentleman-Programming/engram
Overview
Engram is a persistent memory system designed for AI coding agents, supporting SQLite + FTS5 full-text search, and exposed via CLI, HTTP API, and MCP server. It works with any MCP-compatible agent, such as Claude Code, OpenCode, Gemini CLI, and more. Engram provides a single Go binary with no additional dependencies, enabling local or cloud deployment. With Engram, AI agents can retain memory beyond sessions, improving coding efficiency and consistency.
Capabilities
- ▪Persistent memory storage
- ▪Full-text search capability
- ▪Multi-agent support
- ▪Local or cloud deployment
- ▪Zero dependencies
Use cases
Setup
brew install gentleman-programming/tap/engram
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
No, not usually — agents start automatically.
Most of the time, manual startup is not required.
Only when an agent forgets to use Engram after long-running sessions.
Manual configuration is needed only if the agent fails to use Engram after extended sessions.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.